ARCHIVES
VOL. 2, ISSUE 4 (2026)
Explainable artificial intelligence for cybersecurity: Improving threat detection, transparency and trust
Authors
Harry Chandra Tanuwidjaja
Abstract
The increasing sophistication of cyber threats has encouraged organizations to adopt artificial intelligence (AI) and machine learning (ML) for threat detection, intrusion identification, malware classification, and security monitoring. Although AI-based systems can process large volumes of security data and identify complex patterns, many advanced models operate as black boxes, making their decisions difficult for security professionals to understand and validate. Explainable Artificial Intelligence (XAI) addresses this limitation by providing interpretable information about how AI systems reach particular predictions or classifications. This article examines the role of XAI in cybersecurity, focusing on threat detection, transparency, interpretability, and trust. It discusses the application of explanation techniques to intrusion detection, the importance of meaningful explanations for security analysts, the relationship between explainability and model trust, and challenges involving explanation quality, computational cost, adversarial manipulation, and standardization. The article argues that explainability should be considered an integral component of trustworthy AI-based cybersecurity systems rather than merely an additional feature.
Download
Pages:21-24
How to cite this article:
Harry Chandra Tanuwidjaja " Explainable artificial intelligence for cybersecurity: Improving threat detection, transparency and trust". World Journal of Advanced Research
, Vol 2, Issue 4, 2026, Pages 21-24
Pdf, Certificate, Cover Page, Index Page, Editorial Page, Accept Letter
Please enter the email address corresponding to this article submission.
